6945 papers
This paper presents the first systematic analysis of Attack Graph and Intrusion Detection System integration, proposing a novel unifying lifecycle framework that establishes a continuous feedback loop to enhance threat detection and incident response.
This paper demonstrates that Large Vision Language Models (LVLMs) develop human-aligned visual representations by quantifying their correspondence with EEG signals, revealing that intermediate layers, multimodal architecture, and downstream visual performance are key drivers of this neural alignment.
This paper proposes a retrieval-augmented framework for text-to-CT generation that leverages a 3D vision-language encoder to retrieve semantically related clinical cases and their anatomical annotations as structural proxies, thereby enhancing image fidelity and spatial controllability in a realistic inference setting without requiring ground-truth annotations.
This paper proposes an adaptive control framework for Euler-Lagrange systems that guarantees user-defined time-varying state and input constraints under uncertainties and disturbances by integrating a time-varying barrier Lyapunov function with a saturated control law, supported by an offline feasibility condition and validated through real-time helicopter experiments.
HDR-NSFF is a novel framework that reconstructs dynamic high dynamic range (HDR) radiance fields from monocular videos by shifting from 2D pixel alignment to 4D spatio-temporal modeling, utilizing exposure-invariant motion estimation and generative priors to achieve state-of-the-art view synthesis while introducing the first real-world HDR-GoPro dataset for evaluation.
This paper presents a large-scale comparative study using the Epic ReduAct dataset and over 3,000 human participants to demonstrate that while humans rely on sparse, semantically critical cues for egocentric action recognition, state-of-the-art AI models degrade more gradually by depending on contextual and low-level features, revealing fundamental divergences in how humans and machines process spatial and spatiotemporal information.
CORE-Acu is a neuro-symbolic framework for acupuncture clinical decision support that integrates structured reasoning traces, a knowledge graph-based safety verification system, and a specialized loss function to ensure interpretable, hallucination-free, and strictly safe treatment recommendations, outperforming standard LLMs with zero observed safety violations.
EndoSERV is a novel vision-based navigation system for endoluminal robots that overcomes challenges like tissue deformation and label scarcity by combining segment-to-structure odometry with real-to-virtual transfer learning to achieve accurate localization without requiring real-world pose labels.
This paper investigates the computational complexity of context-free, pushdown, and one-counter automata based on the number of "turns" (switches between increasing and decreasing stack height) in accepting computations, proving that determining whether this number is bounded is undecidable, establishing non-recursive trade-offs between automata types, and demonstrating an infinite hierarchy of complexity classes defined by sublinear turn bounds.
The paper proposes DS-DGA-GCN, an adaptive graph learning model that integrates diversity- and similarity-aware dynamic graph attention with a Network Feature Scoring system to effectively detect organized fake reviewer groups in dynamic networks, achieving state-of-the-art performance on real-world datasets.
This paper reviews and analyzes various coordination schemes between Transmission and Distribution System Operators (TSOs and DSOs) to effectively integrate Distributed Energy Resources, aiming to maintain system balance and prevent network congestion while overcoming technical and market challenges associated with the ongoing energy transition.
This paper introduces HIMoS, a hierarchical multi-modal planning framework that enables Autonomous Underwater Vehicles to efficiently search for and sample sparse benthic targets like coral colonies at a fixed altitude by integrating a global topological route optimizer with a local differentiable belief propagation planner, thereby outperforming traditional exhaustive and adaptive sampling strategies in high-fidelity simulations.
The paper introduces PRIME, a two-stage iterative algorithm that combines pruned graph search with an Adaptive Sign Gradient Method to efficiently solve the Token Graph Routing Problem on blockchain platforms, significantly outperforming existing baselines like Uniswap in both execution price and computational speed.
This paper investigates the computational complexity of extending fixed storyline layouts by inserting missing characters to minimize the local crossing number, proving the problem is W[1]-hard when parameterized by the number of inserted characters and active characters, but fixed-parameter tractable when parameterized by the sum of active characters and the local crossing number.
This paper introduces ERASE, a large-scale benchmark designed to align machine unlearning evaluation with real-world recommender system constraints by covering diverse tasks, datasets, and algorithms to systematically analyze the effectiveness and robustness of current unlearning methods.
PhaForce is a phase-scheduled visuomotor policy that enhances contact-rich manipulation by coordinating a slow, vision-dominant diffusion planner with a fast, force-driven corrector to enable high-frequency, phase-aware residual corrections, achieving an 86% success rate and superior adaptability compared to existing baselines.
The paper proposes SOT-GLP, a novel few-shot adaptation method for vision-language models that employs shared sparse optimal transport to partition visual regions among class-specific local prompts while maintaining global alignment, thereby achieving state-of-the-art performance in both classification accuracy and out-of-distribution detection by preserving the native feature geometry.
This paper addresses the scalability challenges of state-space analysis in large-scale renewable power systems by leveraging system symmetry to define distinct inner-group and group-grid eigenvalue patterns and introducing a novel group participation factor for stability analysis and targeted optimization.
This paper introduces VLA, a prior-guided framework that enhances robotic manipulation by modeling discrete world-knowledge variations relative to an explicit current state prior, rather than predicting absolute future states, thereby achieving state-of-the-art performance and efficiency through its novel components: the Prior-Guided World Knowledge Extractor, Latent World Variation Quantization, and Conditional Variation Attention.
This paper introduces UniDiffDA, a unified analytical framework that decomposes diffusion-based data augmentation into three core components to enable a systematic, fair benchmarking of diverse methods across low-data classification tasks, ultimately offering practical design insights and reproducible code.